eval.py

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Validate a trained YOLOv5 model accuracy on a custom dataset

Usage:
    $ python path/to/val.py --weights yolov5s.pt --data coco128.yaml --img 640

"""

import argparse
import json
import os
import sys
sys.path.append('.')
from pathlib import Path

import numpy as np
import torch
from tqdm import tqdm

FILE = Path(__file__).resolve()
ROOT = FILE.parents[0]  # YOLOv5 root directory
if str(ROOT) not in sys.path:
    sys.path.append(str(ROOT))  # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
from od.models.modules.experimental import attempt_load
from utils.callbacks import Callbacks
from od.data.datasets import create_dataloader
from utils.general import (LOGGER, check_dataset, check_img_size, check_requirements, check_yaml,
                           coco80_to_coco91_class, colorstr, emojis, increment_path, non_max_suppression, print_args,
                           scale_coords, xywh2xyxy, xyxy2xywh)
from utils.metrics import ConfusionMatrix, ap_per_class, box_iou
from utils.plots import output_to_target, plot_images, plot_val_study
from utils.torch_utils import select_device, time_sync


def save_one_txt(predn, save_conf, shape, file):
    # Save one txt result
    gn = torch.tensor(shape)[[1, 0, 1, 0]]  # normalization gain whwh
    for *xyxy, conf, cls in predn.tolist():
        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
        line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
        with open(file, 'a') as f:
            f.write(('%g ' * len(line)).rstrip() % line + '\n')


def save_one_json(predn, jdict, path, class_map):
    # Save one JSON result {"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}
    image_id = int(path.stem) if path.stem.isnumeric() else path.stem
    box = xyxy2xywh(predn[:, :4])  # xywh
    box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
    for p, b in zip(predn.tolist(), box.tolist()):
        jdict.append({
            'image_id': image_id,
            'category_id': class_map[int(p[5])],
            'bbox': [round(x, 3) for x in b],
            'score': round(p[4], 5)})


def process_batch(detections, labels, iouv):
    """
    Return correct predictions matrix. Both sets of boxes are in (x1, y1, x2, y2) format.
    Arguments:
        detections (Array[N, 6]), x1, y1, x2, y2, conf, class
        labels (Array[M, 5]), class, x1, y1, x2, y2
    Returns:
        correct (Array[N, 10]), for 10 IoU levels
    """
    correct = np.zeros((detections.shape[0], iouv.shape[0])).astype(bool)
    iou = box_iou(labels[:, 1:], detections[:, :4])
    correct_class = labels[:, 0:1] == detections[:, 5]
    for i in range(len(iouv)):
        x = torch.where((iou >= iouv[i]) & correct_class)  # IoU > threshold and classes match
        if x[0].shape[0]:
            matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()  # [label, detect, iou]
            if x[0].shape[0] > 1:
                matches = matches[matches[:, 2].argsort()[::-1]]
                matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
                # matches = matches[matches[:, 2].argsort()[::-1]]
                matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
            correct[matches[:, 1].astype(int), i] = True
    return torch.tensor(correct, dtype=torch.bool, device=iouv.device)


@torch.no_grad()
def run(
        data,
        weights=None,  # model.pt path(s)
        batch_size=32,  # batch size
        imgsz=640,  # inference size (pixels)
        conf_thres=0.001,  # confidence threshold
        iou_thres=0.6,  # NMS IoU threshold
        task='val',  # train, val, test, speed or study
        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
        workers=8,  # max dataloader workers (per RANK in DDP mode)
        single_cls=False,  # treat as single-class dataset
        augment=False,  # augmented inference
        verbose=False,  # verbose output
        save_txt=False,  # save results to *.txt
        save_hybrid=False,  # save label+prediction hybrid results to *.txt
        save_conf=False,  # save confidences in --save-txt labels
        save_json=False,  # save a COCO-JSON results file
        project='runs/val',  # save to project/name
        name='exp',  # save to project/name
        exist_ok=False,  # existing project/name ok, do not increment
        half=True,  # use FP16 half-precision inference
        model=None,
        dataloader=None,
        save_dir=Path(''),
        plots=True,
        callbacks=Callbacks(),
        compute_loss=None,
):
    # Initialize/load model and set device
    training = model is not None
    if training:  # called by train.py
        device, pt, jit, engine = next(model.parameters()).device, True, False, False  # get model device, PyTorch model
        half &= device.type != 'cpu'  # half precision only supported on CUDA
        model.half() if half else model.float()
    else:  # called directly
        device = select_device(device, batch_size=batch_size)

        # Directories
        save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
        (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir

        # Load model
        pt = True
        model = attempt_load(weights).to(device)  # load FP32 model
        imgsz = check_img_size(imgsz, s=model.stride.max())  # check img_size
        
        # Data
        data = check_dataset(data)  # check
    stride = model.stride.max()
    # Configure
    model.info()
    model.eval()
    cuda = device.type != 'cpu'
    is_coco = isinstance(data.get('val'), str) and data['val'].endswith(f'coco{os.sep}val2017.txt')  # COCO dataset
    nc = 1 if single_cls else int(data['nc'])  # number of classes
    iouv = torch.linspace(0.5, 0.95, 10, device=device)  # iou vector for mAP@0.5:0.95
    niou = iouv.numel()

    # Dataloader
    if not training:
        if pt and not single_cls:  # check --weights are trained on --data
            ncm = model.detection.nc
            assert ncm == nc, f'{weights[0]} ({ncm} classes) trained on different --data than what you passed ({nc} ' \
                              f'classes). Pass correct combination of --weights and --data that are trained together.'
        #model.warmup(imgsz=(1 if pt else batch_size, 3, imgsz, imgsz))  # warmup
        pad = 0.0 if task in ('speed', 'benchmark') else 0.5
        rect = False if task == 'benchmark' else pt  # square inference for benchmarks
        task = task if task in ('train', 'val', 'test') else 'val'  # path to train/val/test images
        dataloader = create_dataloader(data[task],
                                       imgsz,
                                       batch_size,
                                       stride,
                                       single_cls,
                                       pad=pad,
                                       rect=False,
                                       workers=workers,
                                       prefix=colorstr(f'{task}: '))[0]

    seen = 0
    confusion_matrix = ConfusionMatrix(nc=nc)
    names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)}
    class_map = coco80_to_coco91_class() if is_coco else list(range(1000))
    s = ('%20s' + '%11s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', 'mAP@.5', 'mAP@.5:.95')
    dt, p, r, f1, mp, mr, map50, map = [0.0, 0.0, 0.0], 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
    loss = torch.zeros(3, device=device)
    jdict, stats, ap, ap_class = [], [], [], []
    callbacks.run('on_val_start')
    pbar = tqdm(dataloader, desc=s, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}')  # progress bar
    for batch_i, (im, targets, paths, shapes) in enumerate(pbar):
        callbacks.run('on_val_batch_start')
        t1 = time_sync()
        if cuda:
            im = im.to(device, non_blocking=True)
            targets = targets.to(device)
        im = im.half() if half else im.float()  # uint8 to fp16/32
        im /= 255  # 0 - 255 to 0.0 - 1.0
        nb, _, height, width = im.shape  # batch size, channels, height, width
        t2 = time_sync()
        dt[0] += t2 - t1

        # Inference
        out, train_out = model(im) if training else model(im)  # inference, loss outputs
        dt[1] += time_sync() - t2

        # Loss
        if compute_loss:
            loss += compute_loss([x.float() for x in train_out], targets)[1]  # box, obj, cls

        # NMS
        targets[:, 2:] *= torch.tensor((width, height, width, height), device=device)  # to pixels
        lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else []  # for autolabelling
        t3 = time_sync()
        out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls)
        dt[2] += time_sync() - t3

        # Metrics
        for si, pred in enumerate(out):
            labels = targets[targets[:, 0] == si, 1:]
            nl, npr = labels.shape[0], pred.shape[0]  # number of labels, predictions
            path, shape = Path(paths[si]), shapes[si][0]
            correct = torch.zeros(npr, niou, dtype=torch.bool, device=device)  # init
            seen += 1

            if npr == 0:    #当模型的输出为0时
                if nl:  #若原图存在标注
                    # stats.append((correct, *torch.zeros((3, 0), device=device)))  #将conf, pcls, tcls都设置为0，但tcls明显不是0 
                    stats.append((correct, *torch.zeros((2, 0), device=device), labels[:, 0]))
                    if plots:
                        confusion_matrix.process_batch(detections=None, labels=labels[:, 0])
                continue

            # Predictions
            if single_cls:
                pred[:, 5] = 0
            predn = pred.clone()
            scale_coords(im[si].shape[1:], predn[:, :4], shape, shapes[si][1])  # native-space pred

            # Evaluate
            if nl:
                tbox = xywh2xyxy(labels[:, 1:5])  # target boxes
                scale_coords(im[si].shape[1:], tbox, shape, shapes[si][1])  # native-space labels
                labelsn = torch.cat((labels[:, 0:1], tbox), 1)  # native-space labels
                correct = process_batch(predn, labelsn, iouv)
                if plots:
                    confusion_matrix.process_batch(predn, labelsn)
            stats.append((correct, pred[:, 4], pred[:, 5], labels[:, 0]))  # (correct, conf, pcls, tcls)

            # Save/log
            if save_txt:
                save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / (path.stem + '.txt'))
            if save_json:
                save_one_json(predn, jdict, path, class_map)  # append to COCO-JSON dictionary
            callbacks.run('on_val_image_end', pred, predn, path, names, im[si])

        # Plot images
        if plots and batch_i < 3:
            plot_images(im, targets, paths, save_dir / f'val_batch{batch_i}_labels.jpg', names)  # labels
            plot_images(im, output_to_target(out), paths, save_dir / f'val_batch{batch_i}_pred.jpg', names)  # pred

        callbacks.run('on_val_batch_end')

    # Compute metrics
    stats = [torch.cat(x, 0).cpu().numpy() for x in zip(*stats)]  # to numpy
    if len(stats) and stats[0].any():
        tp, fp, p, r, f1, ap, ap_class = ap_per_class(*stats, plot=plots, save_dir=save_dir, names=names)
        ap50, ap = ap[:, 0], ap.mean(1)  # AP@0.5, AP@0.5:0.95
        mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean()
        nt = np.bincount(stats[3].astype(int), minlength=nc)  # number of targets per class
    else:
        nt = torch.zeros(1)

    # Print results
    pf = '%20s' + '%11i' * 2 + '%11.3g' * 4  # print format
    LOGGER.info(pf % ('all', seen, nt.sum(), mp, mr, map50, map))

    # Print results per class
    if (verbose or (nc < 50 and not training)) and nc > 1 and len(stats):
        for i, c in enumerate(ap_class):
            LOGGER.info(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))

    # Print speeds
    t = tuple(x / seen * 1E3 for x in dt)  # speeds per image
    if not training:
        shape = (batch_size, 3, imgsz, imgsz)
        LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}' % t)

    # Plots
    if plots:
        confusion_matrix.plot(save_dir=save_dir, names=list(names.values()))
        callbacks.run('on_val_end')

    # Save JSON
    if save_json and len(jdict):
        w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else ''  # weights
        anno_json = str(Path(data.get('path', '../coco')) / 'annotations/instances_val2017.json')  # annotations json
        pred_json = str(save_dir / f"{w}_predictions.json")  # predictions json
        LOGGER.info(f'\nEvaluating pycocotools mAP... saving {pred_json}...')
        with open(pred_json, 'w') as f:
            json.dump(jdict, f)

        try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
            check_requirements(['pycocotools'])
            from pycocotools.coco import COCO
            from pycocotools.cocoeval import COCOeval

            anno = COCO(anno_json)  # init annotations api
            pred = anno.loadRes(pred_json)  # init predictions api
            eval = COCOeval(anno, pred, 'bbox')
            if is_coco:
                eval.params.imgIds = [int(Path(x).stem) for x in dataloader.dataset.im_files]  # image IDs to evaluate
            eval.evaluate()
            eval.accumulate()
            eval.summarize()
            map, map50 = eval.stats[:2]  # update results (mAP@0.5:0.95, mAP@0.5)
        except Exception as e:
            LOGGER.info(f'pycocotools unable to run: {e}')

    # Return results
    model.float()  # for training
    if not training:
        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
    maps = np.zeros(nc) + map
    for i, c in enumerate(ap_class):
        maps[c] = ap[i]
    return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t


def parse_opt():
    parser = argparse.ArgumentParser()
    parser.add_argument('--data', type=str, default='configs/data.yaml', help='dataset.yaml path')
    parser.add_argument('--weights', nargs='+', type=str, default='runs/train/exp/weights/last.pt', help='model.pt path(s)')
    parser.add_argument('--batch-size', type=int, default=8, help='batch size')
    parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)')
    parser.add_argument('--conf-thres', type=float, default=0.001, help='confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.6, help='NMS IoU threshold')
    parser.add_argument('--task', default='val', help='train, val, test, speed or study')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--workers', type=int, default=10, help='max dataloader workers (per RANK in DDP mode)')
    parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset')
    parser.add_argument('--augment', action='store_true', help='augmented inference')
    parser.add_argument('--verbose', action='store_true', help='report mAP by class')
    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
    parser.add_argument('--save-hybrid', action='store_true', help='save label+prediction hybrid results to *.txt')
    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
    parser.add_argument('--save-json', action='store_true', help='save a COCO-JSON results file')
    parser.add_argument('--project', default=ROOT / 'runs/val', help='save to project/name')
    parser.add_argument('--name', default='exp', help='save to project/name')
    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
    opt = parser.parse_args()
    opt.data = check_yaml(opt.data)  # check YAML
    opt.save_json |= opt.data.endswith('coco.yaml')
    opt.save_txt |= opt.save_hybrid
    print_args(vars(opt))
    return opt


def main(opt):
    # check_requirements(requirements=ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))

    if opt.task in ('train', 'val', 'test'):  # run normally
        if opt.conf_thres > 0.001:  # https://github.com/ultralytics/yolov5/issues/1466
            LOGGER.info(emojis(f'WARNING: confidence threshold {opt.conf_thres} > 0.001 produces invalid results ⚠️'))
        run(**vars(opt))

    else:
        weights = opt.weights if isinstance(opt.weights, list) else [opt.weights]
        opt.half = True  # FP16 for fastest results
        if opt.task == 'speed':  # speed benchmarks
            # python val.py --task speed --data coco.yaml --batch 1 --weights yolov5n.pt yolov5s.pt...
            opt.conf_thres, opt.iou_thres, opt.save_json = 0.25, 0.45, False
            for opt.weights in weights:
                run(**vars(opt), plots=False)

        elif opt.task == 'study':  # speed vs mAP benchmarks
            # python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n.pt yolov5s.pt...
            for opt.weights in weights:
                f = f'study_{Path(opt.data).stem}_{Path(opt.weights).stem}.txt'  # filename to save to
                x, y = list(range(256, 1536 + 128, 128)), []  # x axis (image sizes), y axis
                for opt.imgsz in x:  # img-size
                    LOGGER.info(f'\nRunning {f} --imgsz {opt.imgsz}...')
                    r, _, t = run(**vars(opt), plots=False)
                    y.append(r + t)  # results and times
                np.savetxt(f, y, fmt='%10.4g')  # save
            os.system('zip -r study.zip study_*.txt')
            plot_val_study(x=x)  # plot


if __name__ == "__main__":
    opt = parse_opt()
    main(opt)